bsybin

Logs / Notes

Notes imported from my Obsidian daily track.

  • An Introduction to Mechanistic Interpretability – Neel Nanda IASEAI 2025 Jun 19, 2026
  • Analysing encoded concepts in transformer language models Jul 06, 2026
  • Current Open research Jun 17, 2026
  • Debating with More Persuasive LLMs Leads to More Truthful Answers Jun 18, 2026
  • Deep Learning Our Miraculous Year 19901991 Jun 03, 2026
  • Deep Neural Network properties Jun 04, 2026
  • Differential Neural Computer Jun 13, 2026
  • EVERYTHING, EVERYWHERE, ALL AT ONCE IS MECHANISTIC INTERPRETABILITY IDENTIFIABLE Jun 22, 2026
  • Finding Manifolds With Bilinear Autoencoders Jul 07, 2026
  • Gao, Jun et al. “Representation Degeneration Problem in Training Natural Language Generation Models. Jun 19, 2026
  • Graph Rag Jun 12, 2026
  • How can AI help India Jul 11, 2026
  • Important Links Jun 01, 2026
  • Information Theory Jun 16, 2026
  • LLM - A survey Jun 14, 2026
  • LLM Self-Correction in Vision Language Action Models via Simulation-Driven Optimization Jul 16, 2026
  • Liner Representation hypothesis Jul 09, 2026
  • Maistros A greek LLM through knowledge distillation Jun 17, 2026
  • Manifold Hypothesis Jul 09, 2026
  • Mech Interp, Safety, Alignment Research Map Jun 21, 2026
  • Mnist Dataset Jun 28, 2026
  • NOT ALL LANGUAGE MODEL FEATURES ARE ONE-DIMENSIONALLY LINEAR Jun 23, 2026
  • Noticing The watcher - LLM infer surveillance from blocked feedback Jun 18, 2026
  • Paper Outline Jul 16, 2026
  • Proposal - Building Blocks of intelligence Jul 13, 2026
  • Regularization Jun 21, 2026
  • Sentence Transformers Jul 04, 2026
  • Softmax Jul 05, 2026
  • Sparse Autoencoder Jun 28, 2026
  • The Manifold Turn in Mechanistic Interpretability- A Review of Geo-metric Approaches to Understanding Neural Network Internals Jun 23, 2026
  • The Origins of Representation Manifolds in LargeLanguage Models Jun 21, 2026
  • Untitled Jun 22, 2026
  • Visualizing mnist dataset Jun 13, 2026
  • When Language Overwrites Vision Over Alignmentand Geometric Debiasing in Vision Language Models Jun 22, 2026
  • autoencoders Jun 21, 2026
  • cot-paper-reading May 31, 2026
  • manifold steering revels the shared geometry of neural network representation and behavior Jul 12, 2026
  • polysemantic Jun 28, 2026
  • vanishing gradients Jun 13, 2026
  • world model lecture Jun 02, 2026

© 2026 bsybin